CN110132629A - A method of utilizing SVM prediction rural domestic sewage treatment facility operation validity - Google Patents
A method of utilizing SVM prediction rural domestic sewage treatment facility operation validity Download PDFInfo
- Publication number
- CN110132629A CN110132629A CN201910491864.0A CN201910491864A CN110132629A CN 110132629 A CN110132629 A CN 110132629A CN 201910491864 A CN201910491864 A CN 201910491864A CN 110132629 A CN110132629 A CN 110132629A
- Authority
- CN
- China
- Prior art keywords
- domestic sewage
- treatment facility
- conductivity
- sewage treatment
- rural domestic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 239000010865 sewage Substances 0.000 title claims abstract description 95
- 238000000034 method Methods 0.000 title claims abstract description 34
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 98
- 238000012549 training Methods 0.000 claims abstract description 15
- 238000012706 support-vector machine Methods 0.000 claims abstract description 8
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 claims description 26
- XKMRRTOUMJRJIA-UHFFFAOYSA-N ammonia nh3 Chemical compound N.N XKMRRTOUMJRJIA-UHFFFAOYSA-N 0.000 claims description 20
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 claims description 18
- 229910052698 phosphorus Inorganic materials 0.000 claims description 18
- 239000011574 phosphorus Substances 0.000 claims description 18
- 230000003750 conditioning effect Effects 0.000 claims description 14
- 238000005259 measurement Methods 0.000 claims description 13
- 229910052757 nitrogen Inorganic materials 0.000 claims description 13
- 238000001514 detection method Methods 0.000 claims description 6
- 239000003344 environmental pollutant Substances 0.000 claims description 6
- 231100000719 pollutant Toxicity 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 5
- 238000012544 monitoring process Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims 1
- 238000012360 testing method Methods 0.000 abstract description 6
- 238000012545 processing Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 3
- 238000002790 cross-validation Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 239000010806 kitchen waste Substances 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000010561 standard procedure Methods 0.000 description 2
- 238000005406 washing Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000001154 acute effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012372 quality testing Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 210000002700 urine Anatomy 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- 239000002351 wastewater Substances 0.000 description 1
Classifications
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F3/00—Biological treatment of water, waste water, or sewage
- C02F3/006—Regulation methods for biological treatment
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F3/00—Biological treatment of water, waste water, or sewage
- C02F3/02—Aerobic processes
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F3/00—Biological treatment of water, waste water, or sewage
- C02F3/02—Aerobic processes
- C02F3/12—Activated sludge processes
- C02F3/1236—Particular type of activated sludge installations
- C02F3/1263—Sequencing batch reactors [SBR]
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F3/00—Biological treatment of water, waste water, or sewage
- C02F3/30—Aerobic and anaerobic processes
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F3/00—Biological treatment of water, waste water, or sewage
- C02F3/32—Biological treatment of water, waste water, or sewage characterised by the animals or plants used, e.g. algae
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F3/00—Biological treatment of water, waste water, or sewage
- C02F3/32—Biological treatment of water, waste water, or sewage characterised by the animals or plants used, e.g. algae
- C02F3/327—Biological treatment of water, waste water, or sewage characterised by the animals or plants used, e.g. algae characterised by animals and plants
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M99/00—Subject matter not provided for in other groups of this subclass
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M99/00—Subject matter not provided for in other groups of this subclass
- G01M99/005—Testing of complete machines, e.g. washing-machines or mobile phones
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M99/00—Subject matter not provided for in other groups of this subclass
- G01M99/008—Subject matter not provided for in other groups of this subclass by doing functionality tests
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F2209/00—Controlling or monitoring parameters in water treatment
- C02F2209/001—Upstream control, i.e. monitoring for predictive control
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F2209/00—Controlling or monitoring parameters in water treatment
- C02F2209/005—Processes using a programmable logic controller [PLC]
- C02F2209/006—Processes using a programmable logic controller [PLC] comprising a software program or a logic diagram
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F2209/00—Controlling or monitoring parameters in water treatment
- C02F2209/005—Processes using a programmable logic controller [PLC]
- C02F2209/008—Processes using a programmable logic controller [PLC] comprising telecommunication features, e.g. modems or antennas
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F2209/00—Controlling or monitoring parameters in water treatment
- C02F2209/05—Conductivity or salinity
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F2209/00—Controlling or monitoring parameters in water treatment
- C02F2209/08—Chemical Oxygen Demand [COD]; Biological Oxygen Demand [BOD]
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F2209/00—Controlling or monitoring parameters in water treatment
- C02F2209/10—Solids, e.g. total solids [TS], total suspended solids [TSS] or volatile solids [VS]
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F2209/00—Controlling or monitoring parameters in water treatment
- C02F2209/14—NH3-N
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F2209/00—Controlling or monitoring parameters in water treatment
- C02F2209/16—Total nitrogen (tkN-N)
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F2209/00—Controlling or monitoring parameters in water treatment
- C02F2209/18—PO4-P
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F3/00—Biological treatment of water, waste water, or sewage
- C02F3/02—Aerobic processes
- C02F3/12—Activated sludge processes
- C02F3/1236—Particular type of activated sludge installations
- C02F3/1242—Small compact installations for use in homes, apartment blocks, hotels or the like
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02W—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO WASTEWATER TREATMENT OR WASTE MANAGEMENT
- Y02W10/00—Technologies for wastewater treatment
- Y02W10/10—Biological treatment of water, waste water, or sewage
Landscapes
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Microbiology (AREA)
- Hydrology & Water Resources (AREA)
- Environmental & Geological Engineering (AREA)
- Water Supply & Treatment (AREA)
- Chemical & Material Sciences (AREA)
- Organic Chemistry (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Biotechnology (AREA)
- Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Botany (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Investigating Or Analyzing Materials By The Use Of Electric Means (AREA)
- Activated Sludge Processes (AREA)
Abstract
The invention discloses a kind of method using SVM prediction rural domestic sewage treatment facility operation validity, this method acquires water inlet conductivity and water outlet conductivity simultaneously, and records the operating condition of rural domestic sewage treatment facility；Using intake conductivity and water outlet conductivity as input, the operating condition of rural domestic sewage treatment facility is trained training set using support vector machines as output, constructs the prediction model of rural domestic sewage treatment facility operation validity；The water inlet conductivity and water outlet conductivity for acquiring treatment facility to be predicted, are input in prediction model, obtain prediction result.The method of the present invention will pass in and out water conductivity Testing index and the Results validity of rural domestic sewage treatment facility is associated, and constructs supporting vector machine model and obtain prediction model, and not only forecasting accuracy is high, but also quickly, inexpensively.
Description
Technical field
The present invention relates to technical field of waste water processing more particularly to a kind of utilization SVM prediction domestic sewage in rural areas
The method for the treatment of facility Results validity.
Background technique
With the rapid development of rural economy, life of farmers level has obtained significantly improving, and the environmental construction in rural area
But and asynchronous with economic development, water environment pollution problem is particularly acute, wherein the processing of domestic sewage in rural areas increasingly by
Everybody attention.Since domestic sewage in rural areas has the characteristics that water is small and discharge disperses, China has built a large amount of distributing
The scale of rural domestic sewage treatment facility, these treatment facilities is less, and the water handled daily is generally several tons to several hundred tons,
And geographical location high degree of dispersion, the facility quantity of each counties and districts can reach hundreds and thousands of seats, the long-acting operation pair of these facilities
It is particularly important in the processing of domestic sewage in rural areas and the improvement of rural environment.
Currently, the operational management of rural domestic sewage treatment facility relies primarily on artificial progress, and facility operation is effective
Property especially can not quickly judge the removal effect of the major pollutants such as COD, ammonia nitrogen, TP in sewage at present.If being based on state
Mark method monitors water quality indicator, is sampled in process of supervision with the higher cost of water-quality test, the period is longer, larger workload, difficult
To indicate the Results validity of facility in real time.
For the rural domestic sewage treatment facility that large number of and position disperses, the work of sampling and water-quality test
It measures very huge.Also, it is based on national standard method, the higher cost of detection, timeliness is poor, can not be by obtaining water outlet knot in real time
Fruit targetedly regulates and controls rural domestic sewage treatment facility.And the indexs such as COD, the ammonia nitrogen of use based on spectroscopic methodology principle is fast
Fast detection device, not only costly, and there are certain errors with National Standard Method for price, thus pass through these quick water quality testing meters
When operating condition of the result to judge rural domestic sewage treatment facility that device obtains, tie judgement
Fruit misalignment.
It therefore, is the difficulty of rural sewage treatment facility O&M to the monitoring of rural domestic sewage treatment facility operation validity
Topic.
Summary of the invention
The present invention provides a kind of sides using SVM prediction rural domestic sewage treatment facility operation validity
Method, this method will pass in and out water conductivity Testing index and the Results validity of rural domestic sewage treatment facility is associated, and
It constructs supporting vector machine model and obtains prediction model, not only forecasting accuracy is high, but also quickly, inexpensively.
Specific technical solution is as follows:
A method of utilizing SVM prediction rural domestic sewage treatment facility operation validity, including following step
It is rapid:
(1) several rural domestic sewage treatment facilities are chosen as training set, while it is dirty to acquire life in the countryside in training set
The water inlet conductivity and water outlet conductivity of water processing establishment, and record the operation feelings of corresponding rural domestic sewage treatment facility
Condition；
(2) using intake conductivity and water outlet conductivity as input, the operating condition of rural domestic sewage treatment facility is made
For output, training set is trained using support vector machines, constructs the pre- of rural domestic sewage treatment facility operation validity
Survey model；
(3) the water inlet conductivity and water outlet conductivity for acquiring rural domestic sewage treatment facility to be predicted, are input to step
Suddenly in (2) resulting prediction model, prediction result is obtained.
In the present invention, the domestic sewage in rural areas refers to sewage caused by rural resident's life, specifically includes three classes
Sewage, it may be assumed that through septic tank treated excrement and urine waste, kitchen waste water and washing sewage, major pollutants COD, total nitrogen, ammonia
Nitrogen, total phosphorus and ss suspended solid.The rural domestic sewage treatment facility refers to that the processing for handling domestic sewage in rural areas is set
It sets.
It is found through experiment that for above-mentioned rural domestic sewage treatment facility, conductivity of intaking and water outlet conductivity with
There are correlations between the Results validity of rural domestic sewage treatment facility, water inlet conductivity and water outlet conductivity can be made
It substitutes into supporting vector machine model for input, and is trained according to the operating condition result of rural domestic sewage treatment facility,
The prediction model of rural domestic sewage treatment facility operation validity is constructed, and then realizes rural domestic sewage treatment facility operation
The prediction of validity.
Prediction result to guarantee prediction model is more accurate, and in step (1), sample size is at least big in the training set
In 120~150.
Since conductivity value is related with water temperature, this field generally using 20 DEG C or 25 DEG C of water temperature when conductivity value as ginseng
Than being corrected, and conventional conductivity meter can generally automatically correct.It need to only guarantee the conductivity of measurement using identical in the present invention
Standard is corrected.
Rural domestic sewage treatment facility of the present invention is A2O treatment facility, artificial wetland treatment facility, SBR processing
At least one of facility and aerating filter treatment facility.Above-mentioned rural domestic sewage treatment facility is by water inlet conditioning tank and dirt
Water treatment facilities two parts form, and wet well is equipped at the water outlet of sewage-treatment plant.
In step (1), the operating condition is effectively operation or invalid operation；
Effective operation and the method for discrimination run in vain are as follows: if rural domestic sewage treatment facility is to life in the countryside dirt
Removal rate >=percentage threshold of the COD of water, ammonia nitrogen, total phosphorus and any one index in suspended matter, and do not occur COD,
Ammonia nitrogen, total nitrogen, the case where aqueous concentration of any two index is greater than influent concentration in total phosphorus, then be judged to effectively running；Instead
Be then invalid operation；
The percentage threshold is 20%~70%.
Percentage threshold can be set according to the actual situation, test discovery, and the size setting of percentage threshold does not influence
The applicability of the method for the present invention.
Further, in step (1),
The water inlet conductivity measures in the conditioning tank of rural domestic sewage treatment facility, and minute is in conditioning tank
After elevator pump opens 15min；
The water outlet conductivity measures in the wet well of rural domestic sewage treatment facility, surveys simultaneously with water inlet conductivity
It is fixed；
The mensuration mode for the conductivity and water outlet conductivity of intaking are as follows: the water determination electricity in acquisition conditioning tank or in wet well
Conductivity value；Alternatively, directlying adopt the water in on-line monitoring conductivity meter measurement conditioning tank or in wet well.
Preferably, after elevator pump opens 15min, while each measurement water inlet conductivity and water outlet conductivity are primary, this
Every 15 minutes, each detection water inlet conductivity and water outlet conductivity were primary afterwards, and co-continuous measurement 3~4 times is averaged work respectively
For the water inlet conductivity value and water outlet conductivity value of detection-phase；
While each detection water inlet conductivity and water outlet conductivity, rural domestic sewage treatment facility is measured respectively
The concentration of COD, ammonia nitrogen, total nitrogen, total phosphorus and suspended matter in conditioning tank and wet well, it is dense in inflow and outflow to calculate each pollutant
Concentration of the average value of degree as the COD of detection-phase, ammonia nitrogen, total nitrogen, total phosphorus and suspended matter, for judging domestic sewage in rural areas
The operating condition for the treatment of facility.
Further, in step (2), the conductivity that will first intake respectively and water outlet conductivity are substituted into mapminmax function
It is normalized, then is input in support vector machines；
The formula of mapminmax function are as follows: y=(x-xmin)/(xmax-xmin) (1)；
In formula (1), y is the measured data of water inlet conductivity or water outlet conductivity after normalized, and x is at normalization
The measured data of water inlet conductivity or water outlet conductivity before reason, xminFor the minimum value in x, xmaxFor the maximum value in x；
The rural domestic sewage treatment facility effectively run is labeled as 1, the rural domestic sewage treatment run in vain is set
It applies labeled as -1.
Further, in step (2), using the tool box Libsvm training pattern, the training include penalty parameter c and
The optimization of RBF kernel functional parameter g；
The optimization is carried out according to K-CV cross validation combination grid optimizing, specially uses SVMcgForClass function
It is preferred to penalty parameter c and kernel functional parameter g progress two-wheeled, obtain the optimal solution of penalty parameter c and kernel functional parameter g.
Compared with prior art, the invention has the following advantages:
(1) the method for the present invention will pass in and out the Results validity of water conductivity Testing index and rural domestic sewage treatment facility
It is associated, and constructs supporting vector machine model and obtain prediction model, not only forecasting accuracy is high, but also quickly, inexpensively.
(2) relative to conventional standard detecting method (time for most needing 30min or so fastly), prediction technique of the present invention can
To realize quick predict, be conducive to the progress of subsequent facility regulation.
Detailed description of the invention
Fig. 1 is stream of the present invention using the method for SVM prediction rural domestic sewage treatment facility operation validity
Cheng Tu.
Fig. 2 is the selection result figure of the best penalty parameter c of rougher process and kernel functional parameter g in embodiment 1.
Fig. 3 is carefully to select the best penalty parameter c of process and the selection result figure of kernel functional parameter g in embodiment 1.
Fig. 4 is the comparison diagram of prediction result and actual result in embodiment 1.
Fig. 5 is the comparison diagram of prediction result and actual result in embodiment 2.
Fig. 6 is the comparison diagram of prediction result and actual result in embodiment 3.
Specific embodiment
The invention will be further described combined with specific embodiments below, and what is be exemplified below is only specific implementation of the invention
Example, but protection scope of the present invention is not limited only to this.
Embodiment 1
A method of using SVM prediction rural domestic sewage treatment facility operation validity, specific steps are such as
Under:
(1) 164, Yangtze River Delta Area rural domestic sewage treatment facility is chosen, which includes
The A of mainstream2O treatment facility, artificial wetland treatment facility, SBR treatment facility and aerating filter facility, treatment scale 5-160t/d
Differ；All facilities are made of conditioning tank and sewage-treatment plant two parts, and the water inlet end for conditioning tank of intaking is equipped with elevator pump,
Wet well is equipped at the water outlet of sewage-treatment plant.The domestic sewage in rural areas of above-mentioned facility processing is by through septic tank treated excrement
Urinate sewage, kitchen waste water and washing sewage composition, major pollutants COD, total nitrogen, ammonia nitrogen, total phosphorus and suspended matter；
Measure the water inlet conductivity and water outlet conductivity of rural domestic sewage treatment facility, specific measuring method are as follows:
After elevator pump opens 15min, while the water sample in conditioning tank and wet well is acquired, measurement obtains intaking for the first time
Conductivity value and first time water outlet conductivity value；After 15 minutes, measurement obtains second of water inlet conductivity value and second is discharged
Conductivity value；After 30 minutes, measurement obtains third time water inlet conductivity value and third time water outlet conductivity value；To be intake electricity three times
The value of conductance and the value of water inlet conductivity are average, obtain average water inlet conductivity value and average water outlet conductivity value；
At the same time, measurement three times the COD in rural domestic sewage treatment facility conditioning tank and wet well in water, ammonia nitrogen,
The concentration of total nitrogen, total phosphorus and suspended matter calculates the average value of above-mentioned each pollutant concentration as the COD of detection-phase, ammonia nitrogen, always
The concentration of nitrogen, total phosphorus and suspended matter, for judging the operating condition of rural domestic sewage treatment facility, record measurement conductivity institute
The operating condition of corresponding rural domestic sewage treatment facility, it may be assumed that be effective operation or invalid operation；
If rural domestic sewage treatment facility is to any one in the COD of domestic sewage in rural areas, ammonia nitrogen, total phosphorus and suspended matter
Removal rate >=20% of a index, and do not occur that COD, ammonia nitrogen, total nitrogen, the aqueous concentration of any two index is greater than in total phosphorus
The case where influent concentration, then effectively to run；Conversely, being then invalid operation.
(2) using intake conductivity and water outlet conductivity as input, the operating condition of rural domestic sewage treatment facility is made
For output, 154 groups being randomly selected in 164 groups of data as training set, is trained using support vector machines, building rural area is raw
The prediction model of sewage treatment facility Results validity living；
Specific steps are as follows:
First water inlet conductivity and water outlet conductivity are substituted into mapminmax function respectively and are normalized, then is defeated
Enter into support vector machines；
The formula of mapminmax function are as follows: y=(x-xmin)/(xmax-xmin) (1)；
In formula (1), y is the measured data of water inlet conductivity or water outlet conductivity after normalized, and y is at normalization
The measured data of water inlet conductivity or water outlet conductivity before reason, xminFor the minimum value in x, xmaxFor the maximum value in x；
By the domestic sewage in rural areas facility effectively run be labeled as 1, the domestic sewage in rural areas facility run in vain labeled as-
1。
In training process, realize that support vector machines is trained training set using the tool box Libsvm, building rural area is raw
The prediction model of sewage treatment facility operation standard water discharge situation living, carries out the optimization of penalty parameter c and RBF kernel functional parameter g；
Parameter optimization is carried out according to K-CV cross validation combination grid optimizing, using SVMcgForClass function to punishment
Parameter c and kernel functional parameter g progress two-wheeled is preferred, obtains the optimal solution of penalty parameter c and kernel functional parameter g；
Wherein, the first round is roughing, the variation range respectively [2 of penalty parameter c and kernel functional parameter g-10,210] and [2-10,210]；Second wheel is thin choosing, the variation range respectively [2 of penalty parameter c and kernel functional parameter g0,210] and [2-2,210]。
(3) remaining 10 groups of data are as forecast set, by the water inlet conductance of rural domestic sewage treatment facility to be predicted
Rate and water outlet conductivity are input in step (2) resulting prediction model, obtain prediction result.
Prediction result: the actual effectiveness of 9 facilities is identical as predictive validity, shows that prediction is correct；The reality of 1 facility
Border validity is different from predictive validity, shows prediction error；Therefore the prediction accuracy of forecast set is 90%.
Embodiment 2
" rural domestic sewage treatment facility is to domestic sewage in rural areas except the judgement effectively run to be changed to for the present embodiment
Removal rate >=30% of any one index in COD, ammonia nitrogen, total phosphorus and SS and do not occur COD, ammonia nitrogen, total nitrogen, in total phosphorus
The aqueous concentration of any two index is greater than influent concentration " outside, remaining is used and the identical sample of embodiment 1 and prediction side
Method.
Prediction result: the actual effectiveness of 9 facilities is identical as predictive validity, shows that prediction is correct；The reality of 1 facility
Border validity is different from predictive validity, shows prediction error；Therefore the prediction accuracy of forecast set is 90%.
Embodiment 3
" rural domestic sewage treatment facility is to domestic sewage in rural areas except the judgement effectively run to be changed to for the present embodiment
Removal rate >=70% of any one index in COD, ammonia nitrogen, total phosphorus and SS and do not occur COD, ammonia nitrogen, total nitrogen, in total phosphorus
The aqueous concentration of any two index is greater than influent concentration " outside, remaining is used and the identical sample of embodiment 1 and prediction side
Method.
Prediction result: the actual effectiveness of 8 facilities is identical as predictive validity, shows that prediction is correct；The reality of 2 facilities
Border validity is different from predictive validity, shows prediction error；Therefore the prediction accuracy of forecast set is 80%.
Claims (7)
1. a kind of method using SVM prediction rural domestic sewage treatment facility operation validity, which is characterized in that
The following steps are included:
(1) several rural domestic sewage treatment facilities are chosen as training set, while being acquired in training set at domestic sewage in rural areas
The water inlet conductivity and water outlet conductivity of facility are managed, and records the operating condition of corresponding rural domestic sewage treatment facility；
(2) using intake conductivity and water outlet conductivity as input, the operating condition of rural domestic sewage treatment facility is as defeated
Out, training set is trained using support vector machines, constructs the prediction mould of rural domestic sewage treatment facility operation validity
Type；
(3) the water inlet conductivity and water outlet conductivity for acquiring rural domestic sewage treatment facility to be predicted, are input to step (2)
In resulting prediction model, prediction result is obtained.
2. utilizing the side of SVM prediction rural domestic sewage treatment facility operation validity as described in claim 1
Method, which is characterized in that in step (1), the rural domestic sewage treatment facility is A2O treatment facility, artificial wetland treatment are set
It applies, at least one of SBR treatment facility and aerating filter treatment facility.
3. utilizing the side of SVM prediction rural domestic sewage treatment facility operation validity as described in claim 1
Method, which is characterized in that
In step (1), the operating condition is effectively operation or invalid operation；
Effective operation and the method for discrimination run in vain are as follows: if rural domestic sewage treatment facility is to domestic sewage in rural areas
Removal rate >=percentage threshold of any one index in COD, ammonia nitrogen, total phosphorus and suspended matter, and do not occur COD, ammonia nitrogen,
The aqueous concentration of any two index is greater than the case where influent concentration in total nitrogen, total phosphorus, then is judged to effectively running；It is on the contrary then be
Invalid operation；
The percentage threshold is 20%~70%.
4. utilizing the side of SVM prediction rural domestic sewage treatment facility operation validity as described in claim 1
Method, which is characterized in that in step (1),
The water inlet conductivity measures in the conditioning tank of rural domestic sewage treatment facility, and minute is to be promoted in conditioning tank
After pump opens 15min；
The water outlet conductivity measures in the wet well of rural domestic sewage treatment facility, measures simultaneously with water inlet conductivity；
The mensuration mode for the conductivity and water outlet conductivity of intaking are as follows: the water determination conductivity in acquisition conditioning tank or in wet well
Value；Alternatively, directlying adopt the water in on-line monitoring conductivity meter measurement conditioning tank or in wet well.
5. utilizing the side of SVM prediction rural domestic sewage treatment facility operation validity as claimed in claim 4
Method, which is characterized in that after elevator pump opens 15min, while each measurement water inlet conductivity and water outlet conductivity are primary, hereafter often
Every 15 minutes, each detection water inlet conductivity and water outlet conductivity were primary, and co-continuous measurement 3~4 times is averaged respectively as inspection
The water inlet conductivity value and water outlet conductivity value in survey stage；
While each detection water inlet conductivity and water outlet conductivity, measurement rural domestic sewage treatment facility is adjusted respectively
The concentration of COD, ammonia nitrogen, total nitrogen, total phosphorus and suspended matter in pond and wet well calculate each pollutant concentration in inflow and outflow
Concentration of the average value as the COD of detection-phase, ammonia nitrogen, total nitrogen, total phosphorus and suspended matter, for judging rural domestic sewage treatment
The operating condition of facility.
6. utilizing the side of SVM prediction rural domestic sewage treatment facility operation validity as described in claim 1
Method, which is characterized in that in step (2), first water inlet conductivity and water outlet conductivity are substituted into mapminmax function respectively and carried out
Normalized is to [0,1], then is input in support vector machines；
The formula of mapminmax function are as follows: y=(x-xmin)/(xmax-xmin) (1)；
In formula (1), y is the measured data of water inlet conductivity or water outlet conductivity after normalized, and x is before normalized
Water inlet conductivity or water outlet conductivity measured data, xminFor the minimum value in x, xmaxFor the maximum value in x；
The rural domestic sewage treatment facility effectively run is labeled as 1, the rural domestic sewage treatment facility mark run in vain
It is denoted as -1.
7. utilizing the side of SVM prediction rural domestic sewage treatment facility operation validity as described in claim 1
Method, which is characterized in that in step (2), using the tool box Libsvm training pattern, the training includes penalty parameter c and RBF core
The optimization of function parameter g；
It is described to be optimized for using SVMcgForClass function preferred to penalty parameter c and kernel functional parameter g progress two-wheeled, it obtains
The optimal solution of penalty parameter c and kernel functional parameter g.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910491864.0A CN110132629B (en) | 2019-06-06 | 2019-06-06 | Method for predicting operation effectiveness of rural domestic sewage treatment facility by using support vector machine |
| US17/615,631 US20220316994A1 (en) | 2019-06-06 | 2020-03-09 | A method for predicting operation effectiveness of decentralized sewage treatment facility by using support vector machine |
| PCT/CN2020/078401 WO2020244265A1 (en) | 2019-06-06 | 2020-03-09 | Method for predicting operation effectiveness of rural domestic sewage treatment facility using support vector machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910491864.0A CN110132629B (en) | 2019-06-06 | 2019-06-06 | Method for predicting operation effectiveness of rural domestic sewage treatment facility by using support vector machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110132629A true CN110132629A (en) | 2019-08-16 |
| CN110132629B CN110132629B (en) | 2020-03-10 |
Family
ID=67580645
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910491864.0A Active CN110132629B (en) | 2019-06-06 | 2019-06-06 | Method for predicting operation effectiveness of rural domestic sewage treatment facility by using support vector machine |
Country Status (3)
| Country | Link |
|---|---|
| US (1) | US20220316994A1 (en) |
| CN (1) | CN110132629B (en) |
| WO (1) | WO2020244265A1 (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020244265A1 (en) * | 2019-06-06 | 2020-12-10 | 浙江清华长三角研究院 | Method for predicting operation effectiveness of rural domestic sewage treatment facility using support vector machine |
| CN112964843A (en) * | 2021-01-26 | 2021-06-15 | 清华大学 | Internet of things sensor system for monitoring water quality of sewage treatment facility and monitoring method |
| CN113962493A (en) * | 2021-12-08 | 2022-01-21 | 云南省设计院集团有限公司 | Rapid prediction method based on combined overflow sewage pollutant removal rate |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116718742B (en) * | 2023-05-06 | 2024-05-24 | 四川文韬工程技术有限公司 | Water quality component analysis method for areas without sewage plants |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101712500A (en) * | 2009-10-30 | 2010-05-26 | 艾欧史密斯（上海）水处理产品有限公司 | Water softener control valve |
| CN103235096A (en) * | 2013-04-16 | 2013-08-07 | 广州铁路职业技术学院 | Sewage water quality detection method and apparatus |
| CN107741738A (en) * | 2017-10-20 | 2018-02-27 | 重庆华绿环保科技发展有限责任公司 | A kind of sewage disposal process monitoring intelligent early warning cloud system and sewage disposal monitoring and pre-alarming method |
| CN107977724A (en) * | 2016-10-21 | 2018-05-01 | 复凌科技（上海）有限公司 | A kind of water quality hard measurement Forecasting Methodology of permanganate index |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6408227B1 (en) * | 1999-09-29 | 2002-06-18 | The University Of Iowa Research Foundation | System and method for controlling effluents in treatment systems |
| JP2006110482A (en) * | 2004-10-15 | 2006-04-27 | Mitsubishi Heavy Ind Ltd | Method and system for treating liquid organic waste |
| JP5283831B2 (en) * | 2006-06-16 | 2013-09-04 | 栄児 長塚 | Sewage treatment facility and sewage treatment method |
| US8790517B2 (en) * | 2007-08-01 | 2014-07-29 | Rockwater Resource, LLC | Mobile station and methods for diagnosing and modeling site specific full-scale effluent treatment facility requirements |
| US10539546B2 (en) * | 2014-11-02 | 2020-01-21 | Zhengbiao OUYANG | Measuring phosphorus in wastewater using a self-organizing RBF neural network |
| CN107922213A (en) * | 2015-08-05 | 2018-04-17 | 三菱重工业株式会社 | The control method of water treatment system, power plant and water treatment system |
| CN208436519U (en) * | 2018-03-02 | 2019-01-29 | 苏州爱利过滤技术有限公司 | A kind of new type water purifying control system |
| CN108665119B (en) * | 2018-08-03 | 2021-05-28 | 清华大学 | Water supply pipe network abnormal working condition early warning method |
| CN108931619B (en) * | 2018-08-28 | 2023-09-08 | 大唐（北京）水务工程技术有限公司 | Thermal power plant wastewater treatment equipment life prediction method and device |
| CN109534501B (en) * | 2018-12-03 | 2019-11-05 | 浙江清华长三角研究院 | A kind of monitoring and managing method of rural domestic sewage treatment facility |
| CN110132629B (en) * | 2019-06-06 | 2020-03-10 | 浙江清华长三角研究院 | Method for predicting operation effectiveness of rural domestic sewage treatment facility by using support vector machine |
-
2019
- 2019-06-06 CN CN201910491864.0A patent/CN110132629B/en active Active
-
2020
- 2020-03-09 US US17/615,631 patent/US20220316994A1/en active Pending
- 2020-03-09 WO PCT/CN2020/078401 patent/WO2020244265A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101712500A (en) * | 2009-10-30 | 2010-05-26 | 艾欧史密斯（上海）水处理产品有限公司 | Water softener control valve |
| CN103235096A (en) * | 2013-04-16 | 2013-08-07 | 广州铁路职业技术学院 | Sewage water quality detection method and apparatus |
| CN107977724A (en) * | 2016-10-21 | 2018-05-01 | 复凌科技（上海）有限公司 | A kind of water quality hard measurement Forecasting Methodology of permanganate index |
| CN107741738A (en) * | 2017-10-20 | 2018-02-27 | 重庆华绿环保科技发展有限责任公司 | A kind of sewage disposal process monitoring intelligent early warning cloud system and sewage disposal monitoring and pre-alarming method |
Non-Patent Citations (1)
| Title |
|---|
| 张苒 等: "水质自动监测参数的相关性分析及在水环境监测中的应用", 《中国环境监测》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020244265A1 (en) * | 2019-06-06 | 2020-12-10 | 浙江清华长三角研究院 | Method for predicting operation effectiveness of rural domestic sewage treatment facility using support vector machine |
| CN112964843A (en) * | 2021-01-26 | 2021-06-15 | 清华大学 | Internet of things sensor system for monitoring water quality of sewage treatment facility and monitoring method |
| CN113962493A (en) * | 2021-12-08 | 2022-01-21 | 云南省设计院集团有限公司 | Rapid prediction method based on combined overflow sewage pollutant removal rate |
| CN113962493B (en) * | 2021-12-08 | 2022-08-19 | 云南省设计院集团有限公司 | Rapid prediction method based on combined overflow sewage pollutant removal rate |
Also Published As
| Publication number | Publication date |
|---|---|
| US20220316994A1 (en) | 2022-10-06 |
| CN110132629B (en) | 2020-03-10 |
| WO2020244265A1 (en) | 2020-12-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110132629A (en) | A method of utilizing SVM prediction rural domestic sewage treatment facility operation validity | |
| CN110186505A (en) | A kind of prediction technique of the rural domestic sewage treatment facility standard water discharge situation based on support vector machines | |
| CN110196083A (en) | Monitoring recognition methods, device and the electronic equipment in drainage pipeline networks pollution path | |
| CN112417788A (en) | Water environment pollution analysis system and method based on big data | |
| CN113392523B (en) | Sewage pipe network health condition diagnosis method based on long-duration multi-measuring-point | |
| CN110146122A (en) | A kind of prediction technique of rural domestic sewage treatment facility operation validity | |
| CN101021543A (en) | Water polletion source on-line dynamic tracking monitoring method and system | |
| CN109242367B (en) | Urban sewage treatment rate evaluation and calculation method | |
| CN104730053A (en) | Monitoring method for reflecting running state of urban sewage plant by using three-dimensional fluorescence spectrum | |
| CN110765213A (en) | Method for compiling emission list (dynamic list) of pollution sources in surface water basin | |
| CN105675838B (en) | A based on data-driven2/ O flow water outlet total phosphorus intelligent detecting methods | |
| CN101786675A (en) | Device and method for separating multi-parameter wastewater sources | |
| Li et al. | Effects of sampling strategies and estimation algorithms on total nitrogen load determination in a small agricultural headwater watershed | |
| CN110057410B (en) | Method and device for measuring and calculating pollutant production of daily domestic sewage of per capita | |
| CN115587699A (en) | Water environment quality verification evaluation method and system in designated river area | |
| CN109542150B (en) | Method for adjusting water inlet load of rural domestic sewage treatment facilities | |
| CN111353718B (en) | Wetland and water replenishing engineering environmental effect evaluation method and device based on SWMM and EFDC | |
| CN110790368B (en) | Regional supervision method for rural domestic sewage treatment facility | |
| CN115186960A (en) | Accounting method and device for effective collection and treatment capacity of urban sewage | |
| US11370679B2 (en) | Method for predicting discharge level of effluent from decentralized sewage treatment facilities | |
| CN107010777A (en) | A kind of system for handling microorganism in sewage | |
| CN206515225U (en) | A kind of multi-parameter water quality detector based on spectrum analysis | |
| CN106198911B (en) | A kind of environmental protection water quality monitoring system | |
| CN105929127B (en) | Environmentally friendly water quality real-time monitoring system | |
| CN117805338B (en) | Real-time on-line monitoring method and system for water quality of building water supply pipe network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |